Keywords: Graph Diffusion, Random Walks, Hypo-Elliptic Laplacian, Graph Tensor Networks, Graph Classification
TL;DR: Hypo-ellipctic graph Laplacian is introduced for generalized graph diffusion models with interesting theoretical properties and promising results for capturing long-range interactions.
Abstract: Convolutional layers within graph neural networks operate by aggregating information about local neighbourhood structures; one common way to encode such substructures is through random walks. The distribution of these random walks evolves according to a diffusion equation defined using the graph Laplacian. We extend this approach by leveraging classic mathematical results about hypo-elliptic diffusions. This results in a novel tensor-valued graph operator, which we call the hypo-elliptic graph Laplacian. We provide theoretical guarantees and efficient low-rank approximation algorithms. In particular, this gives a structured approach to capture long-range dependencies on graphs that is robust to pooling. Besides the attractive theoretical properties, our experiments show that this method competes with graph transformers on datasets requiring long-range reasoning but scales only linearly in the number of edges as opposed to quadratically in nodes.
Supplementary Material: zip